Semiconductor device manufacturing system and semiconductor device manufacturing method

Abstract

The invention is to provide a semiconductor manufacturing apparatus system and a semiconductor device manufacturing method for reducing particles having an adverse effect in a manufacturing step of a semiconductor device. A semiconductor device manufacturing system, includes: a semiconductor manufacturing apparatus; and a platform connected to the semiconductor manufacturing apparatus via a network and in which a particle reduction processing is executed, in which the particle reduction processing includes: a step of acquiring a particle characteristic value by using a sample processed by the semiconductor manufacturing apparatus; a step of specifying a component of the semiconductor manufacturing apparatus leading to a particle generation based on the acquired particle characteristic value and correlation data by machine learning; a step of defining a cleaning condition for cleaning the semiconductor manufacturing apparatus based on the specified component; and a step of cleaning the semiconductor manufacturing apparatus using the defined cleaning condition, and the correlation data is correlation data between the particle characteristic value acquired in advance and the component.

The invention claimed is: 
     
         1 . A semiconductor device manufacturing system, comprising:
 a semiconductor manufacturing apparatus; and   a platform connected to the semiconductor manufacturing apparatus via a network and configured to perform particle reduction processing including
 acquiring a plurality of particle characteristic values for each of a plurality of particles of a sample processed by the semiconductor manufacturing apparatus; 
 using stored correlation data, specifying a component of the semiconductor manufacturing apparatus that is correlated with a particle generation based on a ranking of the plurality of particles according to a calculated evaluation value for each of the plurality of particles and the stored correlation data which is stored in a database, wherein each of the calculated evaluation values is determined based on the plurality of acquired particle characteristic values associated with each of the plurality of particles, and a weight assigned to each particle characteristic value, wherein the plurality of acquired particle characteristic values comprises a number of the particle, a composition of the particle, a distribution of the particle with respect to a location on the sample, a shape of the particle, and dimensions of the particle; 
 defining a cleaning condition for cleaning the semiconductor manufacturing apparatus based on the specified component and a stored experience value; and 
 cleaning the semiconductor manufacturing apparatus using the defined cleaning condition, 
 wherein the correlation data stored in the database is correlation data between the specified component and a particle characteristic value that was determined for a previous iteration of the particle reduction processing. 
   
     
     
         2 . The semiconductor device manufacturing system according to  claim 1 , wherein
 the particle reduction processing is executed as an application provided on the platform.   
     
     
         3 . The semiconductor device manufacturing system according to  claim 1 , wherein
 the semiconductor manufacturing apparatus and the platform are configured as cloud computing.   
     
     
         4 . The semiconductor device manufacturing system according to  claim 1 , wherein
 the platform is connected to the semiconductor manufacturing apparatus via a local area network.   
     
     
         5 . The semiconductor device manufacturing system according to  claim 1 , wherein
 a particle measurement apparatus and a particle analysis apparatus are connected to the platform via the network,   the particle characteristic value includes the number of particles and a component of a particle,   the number of particles is measured by the particle measurement apparatus, and   the component of the particle is analyzed by the particle analysis apparatus.   
     
     
         6 . The semiconductor device manufacturing system according to  claim 5 , wherein
 the platform includes a server, and   the semiconductor manufacturing apparatus is a plasma etching apparatus.   
     
     
         7 . The semiconductor device manufacturing system according to  claim 1 , wherein
 a prediction model used for the machine learning is updated every time the particle reduction processing is repeated.   
     
     
         8 . A semiconductor device manufacturing method for manufacturing a semiconductor device using a semiconductor manufacturing apparatus, the semiconductor device manufacturing method comprising:
 a step of acquiring a plurality of particle characteristic values for each of a plurality of particles of a sample processed by the semiconductor manufacturing apparatus;   a step of using stored correlation data for specifying a component of the semiconductor manufacturing apparatus that is correlated with a particle generation based on a ranking of the plurality of particles according to a calculated evaluation value for each of the plurality of particles and the stored correlation data which is stored in a database, wherein each of the calculated evaluation values is determined based on the plurality of acquired particle characteristic values associated with each of the plurality of particles, and a weight assigned to each particle characteristic value, wherein the plurality of acquired particle characteristic values comprises a number of the particle, a composition of the particle, a distribution of the particle with respect to a location on the sample, a shape of the particle, and dimensions of the particle;   a step of defining a cleaning condition for cleaning the semiconductor manufacturing apparatus based on the specified component and a stored experience value; and   a step of cleaning the semiconductor manufacturing apparatus using the defined cleaning condition, wherein   the correlation data stored in the database is correlation data between the specified component and a particle characteristic value that was determined for a previous iteration of the particle reduction processing.   
     
     
         9 . The semiconductor device manufacturing method according to  claim 8 , wherein
 the semiconductor manufacturing apparatus is a plasma etching apparatus, and   the semiconductor device manufacturing method further includes a step of wet cleaning the plasma etching apparatus when it is determined that a particle is not reduced by plasma cleaning after specifying the component of the semiconductor manufacturing apparatus that is correlated with the particle generation.   
     
     
         10 . A semiconductor device manufacturing system, comprising:
 a semiconductor manufacturing apparatus; and   a platform connected to the semiconductor manufacturing apparatus via a network and   which is configured to perform particle reduction processing including   acquiring a plurality of particle characteristic values for each of a plurality of particles of a sample processed by the semiconductor manufacturing apparatus;   specifying a component of the semiconductor manufacturing apparatus that is correlated with a particle generation based on a ranking of the plurality of particles according to a calculated evaluation value for each of the plurality of particles and the stored correlation data which is stored in a database, wherein each of the calculated evaluation values is determined based on the plurality of acquired particle characteristic values associated with each of the plurality of particles, and a weight assigned to each particle characteristic value, wherein the plurality of acquired particle characteristic values comprises a number of the particle, a composition of the particle, a distribution of the particle with respect to a location on the sample, a shape of the particle, and dimensions of the particle;   defining a cleaning condition for cleaning the semiconductor manufacturing apparatus based on the specified component and a stored experience value; and   cleaning the semiconductor manufacturing apparatus using the defined cleaning condition, wherein   the correlation data stored in the database is correlation data between the specified component and a particle characteristic value that was determined for a previous iteration of the particle reduction processing.   
     
     
         11 . The semiconductor device manufacturing system according to  claim 10 , further comprising:
 a graphical user interface in which a map diagram showing a position of a particle on the sample is displayed.   
     
     
         12 . The semiconductor device manufacturing system according to  claim 11 , wherein
 an image of a shape of the particle is displayed by the graphical user interface.   
     
     
         13 . The semiconductor device manufacturing system according to  claim 11 , wherein
 a particle component chart showing a strength of an element component contained in the particle is displayed by the graphical user interface.   
     
     
         14 . The semiconductor device manufacturing system according to  claim 12 , wherein
 a particle component chart showing a strength of an element component contained in the particle is displayed by the graphical user interface.